---
license: mit
---

# Nano语言模型 - 极小模型系列

用于测试的极小语言模型，有以下几个规格。

|   Model Name    |BlockSize|VocabSize|Layers| Embd |Q_Heads|KV_Heads|Hidden|NormEps| #Param |
|-----------------|---------|---------|------|------|-------|--------|------|-------|--------|
|Psycho-230k-base |   512   |  4096   |  8   |  32  |   4   |    2   |  96  | 1e-5  | 229920 |
|Nano-230k-base   |   512   |  4096   |  8   |  32  |   4   |    2   |  96  | 1e-5  | 229920 |

使用2025年12月构造的[4096词表](https://github.com/bd4sur/Nano/blob/master/tokenizer/tokenizer_4096.json)。

## 训练参数

Psycho-230k-base

```
{
    "use_lora": false,
    "lora_rank": 8,
    "lora_alpha": 16,
    "lora_dropout": 0.0,

    "from_checkpoint": "",
    "save_checkpoint_to": "/home/bd4sur/ai/Nano/checkpoint",
    "dataset_path": [
        ["/home/bd4sur/ai/Nano/dataset_preprocessed/pt_train_0.base64", "/home/bd4sur/ai/Nano/dataset_preprocessed/pt_val_0.base64"]
    ],
    "tokenizer_path": "/home/bd4sur/ai/Nano/tokenizer/tokenizer_4096.json",

    "random_seed": 39,
    "batch_size": 256,
    "gradient_accumulation_steps": 1,
    "grad_clip": 1.0,

    "dropout": 0.0,

    "learning_rate": 5e-4,
    "weight_decay": 1e-1,
    "beta1": 0.9,
    "beta2": 0.95,

    "decay_lr": true,
    "warmup_iters": 500,
    "lr_decay_iters": 1e9,
    "min_lr": 6e-5,

    "eval_interval": 100,
    "log_interval": 10,
    "eval_iters": 5,

    "backend": "nccl",
    "device": "cuda",
    "sdp_kernel": "flash",
    "dtype": "bfloat16",
    "use_amp": true
}
```

Nano-230k-base

```
{
    "use_lora": false,
    "lora_rank": 8,
    "lora_alpha": 16,
    "lora_dropout": 0.0,

    "from_checkpoint": "",
    "save_checkpoint_to": "/home/bd4sur/ai/Nano/checkpoint",
    "dataset_path": [
        ["/home/bd4sur/ai/Nano/dataset_preprocessed/pt_1Gtk_512_4096_train.base64", "/home/bd4sur/ai/Nano/dataset_preprocessed/pt_1Gtk_512_4096_valid.base64"]
    ],
    "tokenizer_path": "/home/bd4sur/ai/Nano/tokenizer/tokenizer_4096.json",

    "random_seed": 39,
    "batch_size": 256,
    "gradient_accumulation_steps": 1,
    "grad_clip": 1.0,

    "dropout": 0.0,

    "learning_rate": 5e-4,
    "weight_decay": 1e-1,
    "beta1": 0.9,
    "beta2": 0.95,

    "decay_lr": true,
    "warmup_iters": 500,
    "lr_decay_iters": 1e9,
    "min_lr": 6e-5,

    "eval_interval": 100,
    "log_interval": 10,
    "eval_iters": 5,

    "backend": "nccl",
    "device": "cuda",
    "sdp_kernel": "flash",
    "dtype": "bfloat16",
    "use_amp": true
}
```